app.py

from sentence_transformers import SentenceTransformer
import chromadb
import pandas as pd
import gradio as gr
from datetime import datetime
import tempfile
import os 

# ===== Configuración =====
CHROMA_DIR = "chroma_db"
MODEL_NAME = "mrm8488/multilingual-e5-large-ft-sts-spanish-matryoshka-768-16-5e"
COLLECTION_NAMES = ["spc"]

# ===== 1. Conectar a la base de datos y cargar colecciones =====
print("Conectando a ChromaDB...")
client = chromadb.PersistentClient(path=CHROMA_DIR)
collections = [client.get_collection(name) for name in COLLECTION_NAMES]

# ===== 2. Cargar el modelo =====
print("Cargando modelo...")
model = SentenceTransformer(MODEL_NAME, trust_remote_code=True)
print("✓ Sistema listo")

# ===== 3. Función de búsqueda =====
def semantic_search(query: str, n_results: int = 20):
    print(f"Buscando: {query}")
    
    if not query.strip():
        return pd.DataFrame(), ""
    
    query_embedding = model.encode(query).tolist()

    all_results = []
    for collection in collections:
        results = collection.query(
            query_embeddings=[query_embedding],
            n_results=n_results,
            include=["documents", "metadatas", "distances"]
        )
        cosine_similarities = [1 - dist for dist in results['distances'][0]]
        
        for i in range(len(results['ids'][0])):
            result_dict = {
                'Relevante': False,  # Columna de selección al inicio
                'ID': results['ids'][0][i],
                'Similitud': round(cosine_similarities[i], 4),
                'Texto': results['documents'][0][i],
                'Colección': collection.name
            }
            
            metadata = results['metadatas'][0][i]
            if metadata:
                for key, value in metadata.items():
                    # Si hay URL, convertir a link
                    if key.lower() in ['url', 'link', 'enlace'] and value:
                        result_dict[key] = f'<a href="{value}" target="_blank">🔗 Abrir</a>'
                    else:
                        result_dict[key] = value
            
            all_results.append(result_dict)

    df = pd.DataFrame(all_results).sort_values('Similitud', ascending=False).head(n_results)
    df = df[['Número de Resolución', 'Fecha de Resolución', 'Texto', 'Enlace','Relevante']]
    print(f"Resultados: {len(df)}")
    
    return df, ""

# ===== 4. Función para exportar seleccionados a Excel =====
def export_to_excel(df_with_selection):
    if df_with_selection is None or len(df_with_selection) == 0:
        gr.Warning("No hay datos para exportar")
        return None
    
    # Filtrar solo los marcados como True en la columna 'Relevante'
    df_selected = df_with_selection[df_with_selection['Relevante'] == True].copy()
    
    if len(df_selected) == 0:
        gr.Warning("No has seleccionado ninguna decisión")
        return None
    
    # Quitar la columna de checkbox del export
    df_export = df_selected.drop(columns=['Relevante'])
    
    # Limpiar HTML de los links para Excel
    for col in df_export.columns:
        if df_export[col].dtype == 'object':
            df_export[col] = df_export[col].apply(
                lambda x: x.replace('<a href="', '').replace('" target="_blank">🔗 Abrir</a>', '') 
                if isinstance(x, str) and '<a href=' in x else x
            )
    
    # Guardar en carpeta temporal del sistema
    temp_dir = tempfile.gettempdir()
    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
    filename = os.path.join(temp_dir, f"jurisprudencia_dc_{timestamp}.xlsx")
    df_export.to_excel(filename, index=False, engine='openpyxl')
    
    print(f"✓ Exportado: {filename} ({len(df_export)} registros)")
    gr.Info(f"✓ {len(df_export)} decisiones exportadas. Descargando...")
    return filename

# ===== 5. Interfaz Gradio =====

tema = gr.themes.Soft(
    primary_hue="blue",
).set(
    body_background_fill="*neutral_50",
    body_background_fill_dark="*neutral_50",
    block_background_fill="*neutral_50",
    block_background_fill_dark="*neutral_50",
    input_background_fill="white",
    input_background_fill_dark="white",
)
               
# ===== 5. Interfaz Gradio =====
with gr.Blocks(title="Buscador Jurisprudencia") as demo:
    gr.Markdown("# 🔍 Experto en Protección al Consumidor")
    gr.Markdown("Realiza tu consulta preguntando por temas o introduciendo los hechos del caso")
    
    # Query box
    query_box = gr.Textbox(
        show_label=False, 
        placeholder="Escribe tu consulta y presiona Enter...",
        lines=1
    )
    
    # Tabla de resultados (EDITABLE para marcar checkboxes)
    results_table = gr.Dataframe(
        label="Resultados",
        wrap=True,
        interactive=True,
        datatype=["number", "number", "str", "markdown", 'bool'],
        max_height=600,
        column_widths=["7%", "7%", "55%", "7%", "7%"]
    )
    
    # Botón de exportar abajo a la derecha
    with gr.Row(elem_id="export-row"):
        export_button = gr.Button("📥 Exportar a Excel", variant="primary", size="sm", elem_id="export-btn")
    
    # File output oculto para descargas automáticas
    file_output = gr.File(label="", visible=False)
    
    # Eventos
    query_box.submit(
        semantic_search, 
        [query_box], 
        [results_table, query_box]
    )
    
    export_button.click(
        export_to_excel,
        [results_table],
        [file_output]
    )

demo.launch(
    theme=tema,
    css="""
    /* Bordes gruesos */
    .svelte-u825rv td, 
    .svelte-u825rv th {
        border: 3px solid #888888 !important;
        padding: 12px !important;
    }
    
    .svelte-u825rv table {
        border-collapse: collapse !important;
    }
    
    /* Headers - targetear el span interno */
    .svelte-u825rv th .svelte-8fgf56.multiline.text {
        white-space: normal !important;
        word-wrap: break-word !important;
        text-align: center !important;
        display: block !important;
        line-height: 1.4 !important;
    }
    
    /* Centrar el header button también */
    .svelte-u825rv th .header-button {
        text-align: center !important;
        justify-content: center !important;
    }
    
    /* Checkbox con más sombra */
    input[type="checkbox"] {
        box-shadow: 0 4px 8px rgba(0, 0, 0, 0.3) !important;
        transform: scale(1.2);
    }
    
    /* Botón */
    #export-row { 
        justify-content: flex-end; 
        margin-top: 10px;
    }
    
    #export-btn { 
        max-width: 200px;
        min-width: 150px;
    }
    """
)